Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 12467
    Prev
    Next
    INDEX
    Explanations

    words related to the city or location of Toronto

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Toronto

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Laos
    -0.74
    SPONSORED
    -0.73
    urdue
    -0.72
    heit
    -0.71
    ateurs
    -0.66
    abase
    -0.66
     forgiveness
    -0.63
    acebook
    -0.61
     veterin
    -0.60
     inval
    -0.59
    POSITIVE LOGITS
    ondo
    0.77
    ooth
    0.75
    Ped
    0.70
     Janeiro
    0.70
    onto
    0.69
    IDS
    0.69
    Ïī
    0.69
    idis
    0.66
    undo
    0.66
    iden
    0.65
    Activations Density 0.147%

    No Known Activations